<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
cause-effect-training
This model is a fine-tuned version of DeepPavlov/rubert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3611
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.9012
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 35 | 0.5740 | 0.0 | 0.0 | 0.0 | 0.8204 |
No log | 2.0 | 70 | 0.3980 | 0.0 | 0.0 | 0.0 | 0.8649 |
No log | 3.0 | 105 | 0.3250 | 0.0 | 0.0 | 0.0 | 0.8817 |
No log | 4.0 | 140 | 0.3068 | 0.0 | 0.0 | 0.0 | 0.8887 |
No log | 5.0 | 175 | 0.3042 | 0.0 | 0.0 | 0.0 | 0.8922 |
No log | 6.0 | 210 | 0.3043 | 0.0 | 0.0 | 0.0 | 0.8938 |
No log | 7.0 | 245 | 0.3172 | 0.0 | 0.0 | 0.0 | 0.8926 |
No log | 8.0 | 280 | 0.3193 | 0.0 | 0.0 | 0.0 | 0.8934 |
No log | 9.0 | 315 | 0.3233 | 0.0 | 0.0 | 0.0 | 0.8954 |
No log | 10.0 | 350 | 0.3399 | 0.0 | 0.0 | 0.0 | 0.8973 |
No log | 11.0 | 385 | 0.3208 | 0.0 | 0.0 | 0.0 | 0.9028 |
No log | 12.0 | 420 | 0.3393 | 0.0 | 0.0 | 0.0 | 0.9032 |
No log | 13.0 | 455 | 0.3604 | 0.0 | 0.0 | 0.0 | 0.8985 |
No log | 14.0 | 490 | 0.3603 | 0.0 | 0.0 | 0.0 | 0.9004 |
0.2432 | 15.0 | 525 | 0.3611 | 0.0 | 0.0 | 0.0 | 0.9012 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0